Anthem

I have met the same problem

Thanks for your reply and I get your difficulty~ However, is it possible to public the visda.yaml file? For me, the parameter settings of different datasets are difficult to adjust...

> Hi Bo, I tried the following script, but I got an error. I want to train the model using LA dataset and I added the `image_processor` and `train_num_samples` back...

I am willing to see that you have already noticed this issue. :) I just tried to train the otter-7b on the 'LACONV' splits. And there may be a minor...

Note that I also set the num_epochs=9, following the default settings.